INDEX

Explanations

programming object-related terms and structures in code

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

存于互联网档案馆

-0.85

','$

-0.68

GraphicsUnit

-0.66

 kere

-0.66

varlak

-0.65

áso

-0.64

ιού

-0.64

udnio

-0.64

TagMode

-0.63

ệ

-0.62

POSITIVE LOGITS

obj

0.99

 Sams

0.98

sams

0.95

obj

0.94

 Schuyler

0.91

 McCull

0.88

 sams

0.88

Sams

0.86

 Schilling

0.84

 Schlegel

0.81

Activations Density 0.477%

programming object-related terms and structures in code

No Comments

No Known Activations